Particle Podcast Search Transcripts
particle_podcast_search_transcriptsSearch the podcast catalog by what is said in episodes — by meaning (semantic_search), by exact phrase (keyword_search), or both at once (hybrid ranking). This is THE way to retrieve relevant dialogue, segments, and clips: each result is one segment of one episode with bounded transcript windows pinpointing the highest-relevance lines, plus any highlight clips that overlap the segment inline on the match.
Segments partition an episode's transcript — where start_line and end_line are present, every spoken line belongs to exactly one segment and one segment's end_line + 1 is the next one's start_line. They are contiguous in transcript lines, not in wall-clock seconds: the seconds between one segment's end_seconds and the next's start_seconds contain no transcribed speech. These matches do not carry the line ranges themselves — fetch them with particle_podcast_get_episode and include: ["segments"], where their absence marks an episode segmented by an earlier version, a small share of which do leave lines uncovered. Clips are sparse, engagement-ranked highlights that overlap some segments. There is no separate clip-search tool — relevant clips arrive on these matches, and a known episode's full clip list is particle_podcast_get_episode with include: ["clips"].
A match window defaults to one line of context around each matched line; raise context to widen windows in place instead of fetching the full transcript.
Screening many results? Pass format: "compact". Each match then carries only its identity — episode and podcast slugs, segment id and bounds, segment type, the segment's one-line description, and the relevance score — with no dialogue or clips, at a fraction of the size and latency of the default. Fan out compact searches over companies, themes, or dates, decide which segments matter, then read dialogue only for those: particle_podcast_get_episode with include: ["transcript"] and transcript_start/transcript_end set to the segment's bounds, or this tool again with episode_slug narrowed to that episode.
Use this for "find dialogue about a topic". For "every line naming a person or company" use particle_podcast_find_mentions instead — person_slug and company_slug here narrow ranked results, they don't drive the ranking.
Choosing your query. At least one of semantic_search or keyword_search is required, and they do different jobs:
semantic_searchcarries the idea. Write it as a sentence describing what should be discussed, in the vocabulary a speaker would use. It is paraphrase-tolerant, so it finds the topic however it happens to be worded.keyword_searchcarries words that must be literally spoken. Every word must occur in the same passage, so it is for one or two exact tokens — a ticker, a product name — not for a description. Putting a sentence here returns nothing.Use both when a topic must also contain an exact term. The result is their intersection, which is narrow by design; if that comes back empty,
keyword_match: "ranked"relaxes the keyword side to a relevance hint.
Do not put a name in semantic_search. Resolve it (particle_person_resolve, particle_company_resolve, particle_entity_resolve) and pass the slug — searching for "Sam Altman" as text finds passages that sound like him, while person_slug finds the episodes actually featuring him.
The question's constraints go on the first call. Who is speaking, which person, company or show, which window or language: when the question states it, pass it from the start, because a search without it answers a different question. Hold back only the filters you add on your own (a segment_type, a role, a narrower window) until a search shows the topic has coverage: every filter compounds, and each one can remove all results. If a search returns nothing because of a filter, the error names the parameter responsible and the retry to make — act on it rather than re-issuing variations of the same query, and when a constraint the question stated is what emptied it, say so before showing anything wider.
Note on role. It describes how someone relates to the episode: guest/host/panelist/correspondent mean they spoke, mention means they were talked about. Omitting role covers both and is almost always what you want.
Who is speaking. When the question restricts who speaks by occupation, profession or industry ("medical professionals", "economists", "lawyers"), pass the words themselves as guest_occupation, which resolves an everyday word to the occupation, field or capacity it names, or a code from particle_expertise_resolve as guest_occupation/guest_field (plus guest_standing="established" or guest_practicing=true when credentials matter); never stand the profession in for a filter inside semantic_search. On unresolved_reference, resolve and retry; never drop the filter. A word no occupation names may name a capacity ("founders", "politicians"): pass it as guest_capacity. The filters AND together, so two groups ("founders and VCs") take one call each. The filters keep segments in which such a guest speaks, so a window can also carry the host's lines: each full-format match lists its identified speakers as **Speaker:** rows with their occupation codes, standing and seniority — check them before attributing a line to a credential.
How each line is said. Lines in topic and interview segments end with their speaker statement characteristics, pole labels only, e.g. _[positive · confident · future]_: sentiment (negative/positive), certainty (hedged/confident), specificity (vague/specific) and temporal orientation (past/future). A pole label means the line clearly reads that way; _[neutral]_ means it leans clearly on no axis; no brackets means the line was not read (short lines, intros, ad breaks). With output_format=json they are each line's speaker_statement_characteristics object, middle labels included.
Filtering by how a line is said. Pass speaker_statement_characteristics to keep only lines said a certain way: {"sentiment": ["negative"]} for criticism, {"specificity": ["specific"], "temporal_orientation": ["future"]} for concrete predictions, {"certainty": ["confident"], "sentiment": ["positive"], "temporal_orientation": ["future"]} for a high-conviction outlook. Put the topic, never the tone, in semantic_search. Every matched or mention line then carries labels the filter accepts.
Without a topic. On particle_podcast_search_transcripts, the filter alone with episode_slug, speaker or a guest_ filter (no semantic_search or keyword_search) returns the strongest lines said that way, at most 50, strongest first: an episode's boldest predictions, or a person's most confident claims. Their Match row reads characteristics. For the strongest lines naming a person, company or entity, pass the filter with sort: "strength" on particle_podcast_find_mentions instead.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | How the entity must relate to the episode. Speaking roles: 'guest', 'host', 'panelist', 'correspondent', or 'speaker' for any of them. 'mention' means the entity is talked about rather than speaking. Omit to match both — usually what you want. | |
| sort | No | Sort order. Defaults to relevance. | |
| limit | No | Results per page (1-50, default 10). | |
| since | No | Only segments from episodes published on or after this ISO 8601 date. | |
| until | No | Only segments from episodes published on or before this ISO 8601 date. | |
| cursor | No | Opaque pagination cursor from a previous response. | |
| format | No | Response shape. 'full' (default) carries each match's bounded dialogue windows and overlapping clips. 'compact' returns the same ranked matches with no dialogue — episode and podcast slugs, segment id and bounds, segment type, the segment's one-line description, and the relevance score — at a fraction of the size and latency, because the transcript load and line scoring are skipped. Use it to screen many results (a fan-out over companies, themes, or dates) and read dialogue only for the survivors. | |
| context | No | Lines of surrounding dialogue around each matched line (1-15, default 1). Widens each match window in place — use a larger value instead of fetching the full transcript when a match needs more context. Ignored when format is compact. | |
| speaker | No | Person slug or ID from particle_person_resolve (e.g. 'sam-altman'). Keeps only passages in which this person speaks a line, and only their lines can match: 'did X say Y', where person_slug is 'Y came up in an episode with X'. With keyword_search their own lines must carry every quoted phrase (and every unquoted word under keyword_match=required). A clip of them played on another show does not count, so this finds the original rather than its replays. An empty result does not prove they never said it: narrow with podcast_slug, episode_slug or dates, or try semantic_search. Cannot be combined with the guest_ filters. | |
| language | No | Restrict to episodes of podcasts in this language — ISO 639-1 code (e.g. 'fr'). Matches the podcast's primary language subtag, so 'fr' covers 'fr-FR'. | |
| entity_slug | No | Knowledge-graph entity slug from particle_entity_resolve for the long tail that isn't a person or company — places, organizations, events, products, concepts (e.g. 'germany'). Use person_slug for people and company_slug for companies. | |
| entity_type | No | Narrow to dialogue in episodes that mention any entity of this category — e.g. 'book', 'company', 'movie', 'school'. Use for 'discussions of X that reference some book'. Ignored when person_slug/company_slug/entity_slug names a specific entity, which is strictly narrower. Categories come from particle_catalog. | |
| guest_field | No | Only episodes with a guest listed under this ANZSRC 2020 field of research: a code, slug or title from particle_expertise_resolve (e.g. 'banking-finance-and-investment'). | |
| person_slug | No | Person slug or encoded person ID from particle_person_resolve, particle_entity_resolve, or the guest tools (e.g. 'sam-altman'). Filters results to dialogue featuring this person. For 'every line about X' use particle_podcast_find_mentions instead. | |
| company_slug | No | Company slug, domain, or ID. Resolves to the company's linked entity and applies as a filter. | |
| episode_slug | No | Filter to a specific episode by slug or ID. A particle.pro or Radar episode link also works. | |
| podcast_slug | No | Podcast slug, internal ID, or numeric iTunes ID. A particle.pro or Radar show link also works. | |
| segment_type | No | Segment type filter. | |
| speaker_role | No | Keep only lines whose speaker held one of these roles in the episode: guest, panelist, host, correspondent, or speaker for any of them. ["guest", "panelist"] leaves out the hosts' lines, such as a news show's scripted reads. Every matched line is spoken in one of the roles. No default: omit it to keep every speaker's lines. Not role, which is how person_slug, company_slug or entity_slug relates to the episode. With speaker, keeps that person's lines in these roles; beside the guest_ filters it must name guest or panelist. | |
| keyword_match | No | How UNQUOTED keyword_search words are applied. 'required' (default) excludes any passage missing one of them, which also makes a hybrid call an intersection with semantic_search. Switch to 'ranked' when keyword_search is a loose bag of related words that will not co-occur — then those words only steer relevance. Quoted phrases still filter in both modes: to relax a phrase, remove its quotes rather than switching mode. | |
| output_format | No | Output serialization. 'markdown' (default) returns the LLM-facing rendering. 'json' returns the structured payload as JSON text — use only for programmatic chaining where exact field extraction matters; the JSON shape is larger and noisier for an LLM to read. | |
| guest_capacity | No | Only episodes with a guest who knows their field in this capacity (e.g. 'executive_founder' for founders). It narrows the other filters; particle_expertise_resolve names the capacity an everyday word means. | |
| guest_in_field | No | Only episodes with a guest speaking within their own field (the guest the other guest_ filters select, when given). | |
| guest_standing | No | Only episodes with a guest whose standing is recognized this way: 'established' (conferred by others), 'self_described', or 'unverified'. | |
| keyword_search | No | Words that must literally be spoken. Use for exact tokens a paraphrase would miss — tickers, product names, drug names, model numbers. Every word must appear in the same passage (see keyword_match), so keep it to the one or two words that must be said and put the rest of the idea in semantic_search. Wrap words in double quotes to also require them adjacent and in order in the segment's spoken dialogue — only for short exact strings, never for a sentence. A quoted name matches segments where the name appears in the dialogue, not segments that person speaks in; use person_slug or particle_podcast_find_mentions for a person's appearances. There is no boolean OR: 'a OR b' requires the literal word 'OR', so issue one call per alternative. | |
| guest_seniority | No | Only episodes with a guest at this seniority or above. | |
| semantic_search | No | Vector-similarity search by meaning. Express the query the way you'd describe the topic to a colleague — paraphrase tolerant. Combine with keyword_search for hybrid ranking. Describe a topic, not a name: to find a specific person/company/entity, filter with person_slug / company_slug / entity_slug (or use particle_podcast_find_mentions for every line about them) — and for an exact token like a ticker, use keyword_search. Describe a topic, not a tone: optimistic, skeptical, predictions and other ways something is said go in speaker_statement_characteristics ('AI drug discovery', not 'optimistic predictions about AI drug discovery'). | |
| guest_occupation | No | Only episodes with a guest listed under this occupation: a SOC 2018 or ISCO-08 code, slug or title from particle_expertise_resolve, or a SOC group or everyday name (e.g. 'cardiologists', '29-1212', 'physicians' or 'doctors'). A word with no occupation filters by the field of research or capacity it names: 'oncologists' is field 3211, 'founders' is capacity executive_founder. | |
| guest_practicing | No | Only episodes with a guest who still works in guest_occupation, which must be a SOC 2018 occupation or group (e.g. '29-1212' or 'physicians'). | |
| speaker_statement_characteristics | No | Keep only lines said a certain way. HOW something is said goes here and never in semantic_search: optimistic or bullish → sentiment positive; skeptical, critical or bearish → sentiment negative; predictions or forecasts → temporal_orientation future (add specificity specific for concrete predictions); high conviction → certainty confident; hedging → certainty hedged; concrete claims → specificity specific. The topic goes in semantic_search and who speaks in the guest_ or speaker filters. Labels listed for one axis match any of them; axes combine with AND, so add only the axes the request names. Every matched line carries labels the filter accepts. Example: {"certainty": ["confident"], "temporal_orientation": ["future"]}. |